avsolatorio commited on
Commit
e0f8302
1 Parent(s): 955ebb3

Training in progress, step 8000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81f9391d1a3f7496c17b6f177cb61462c901e62e98a50edb8df8c02773379bd8
3
  size 567860028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5e579fef1b7fd0038c9762b3c4fbb2d4563a550ba39f4cad986867eee7d3381
3
  size 567860028
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a34883662b324dd1a0b9ef793b140ef0ea4d1cf9e31b8ec8a8255e7c14f6ee76
3
  size 1135783354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:165717be452493be82c0e50980d64b28838a8e1ad86c8ce5d28ffc1cf050c018
3
  size 1135783354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4902fcfb33d73ecfa5cb7dbd3cfd13500058abf1d6eae05ae197780b6416694
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f40c0d9a49a814dc52082f9054fc2ffb694380fb521f25163384314e1e0b22ae
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43495fd59fd541eb94253a07f3e011c2581153d25d7fa1816722e70a1a8e7f7f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:173f4a2433232f77939b4d77264600e6f898939c018c908fe5f061eb1c76ed9b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.04172312840819359,
3
- "best_model_checkpoint": "doc-topic-model_eval-03_train-01/checkpoint-7000",
4
- "epoch": 3.4516765285996054,
5
  "eval_steps": 1000,
6
- "global_step": 7000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -189,6 +189,32 @@
189
  "eval_samples_per_second": 559.261,
190
  "eval_steps_per_second": 2.207,
191
  "step": 7000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
192
  }
193
  ],
194
  "logging_steps": 500,
@@ -217,7 +243,7 @@
217
  "attributes": {}
218
  }
219
  },
220
- "total_flos": 158408873454492.0,
221
  "train_batch_size": 4,
222
  "trial_name": null,
223
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.04098295420408249,
3
+ "best_model_checkpoint": "doc-topic-model_eval-03_train-01/checkpoint-8000",
4
+ "epoch": 3.9447731755424065,
5
  "eval_steps": 1000,
6
+ "global_step": 8000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
189
  "eval_samples_per_second": 559.261,
190
  "eval_steps_per_second": 2.207,
191
  "step": 7000
192
+ },
193
+ {
194
+ "epoch": 3.698224852071006,
195
+ "grad_norm": 0.39966270327568054,
196
+ "learning_rate": 1.92603550295858e-05,
197
+ "loss": 0.0403,
198
+ "step": 7500
199
+ },
200
+ {
201
+ "epoch": 3.9447731755424065,
202
+ "grad_norm": 0.42601555585861206,
203
+ "learning_rate": 1.921104536489152e-05,
204
+ "loss": 0.0393,
205
+ "step": 8000
206
+ },
207
+ {
208
+ "epoch": 3.9447731755424065,
209
+ "eval_accuracy": 0.9861601258556911,
210
+ "eval_f1": 0.5412262156448203,
211
+ "eval_loss": 0.04098295420408249,
212
+ "eval_precision": 0.7033825863963854,
213
+ "eval_recall": 0.4398289554062309,
214
+ "eval_runtime": 14.4597,
215
+ "eval_samples_per_second": 560.87,
216
+ "eval_steps_per_second": 2.213,
217
+ "step": 8000
218
  }
219
  ],
220
  "logging_steps": 500,
 
243
  "attributes": {}
244
  }
245
  },
246
+ "total_flos": 181076248886436.0,
247
  "train_batch_size": 4,
248
  "trial_name": null,
249
  "trial_params": null